© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18052
    Prev
    Next
    INDEX
    Explanations

    recursion stopping condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    াড়া
    0.39
     काळ
    0.36
     ගැනීමට
    0.36
    જો
    0.36
     вина
    0.36
    ປ
    0.35
    甠
    0.35
    篂
    0.35
    ग्गा
    0.35
    呥
    0.35
    POSITIVE LOGITS
     stopping
    0.62
     stop
    0.59
     STOP
    0.55
     Stop
    0.55
     stopped
    0.54
    Stopping
    0.52
     stops
    0.51
    STOP
    0.51
     Stopped
    0.50
    stopping
    0.49
    Activations Density 0.006%

    No Known Activations